基于CEEMD和膜计算优化支持向量机的风速预测

发布时间：2018-06-16 00:12

本文选题：互补经验模态分解 + 膜计算优化算法　；参考：《电力系统保护与控制》2017年21期

【摘要】：为提高预测的可靠性和准确性,提出一个基于模态分解理论和膜计算优化算法的混合模型用于风速预测。与现有的风速预测方法相比,该模型提高了预测精度。该模型包括3个主要步骤:为了简化数据的复杂度,通过互补集合经验模式分解(CEEMD)将原始风电功率时间序列分解成几个固有模态函数(IMFs);对每个IMF分量单独建立膜计算优化算法优化支持向量机(MCO-SVR)的模型进行预测;叠加全部IMF分量的预测值作为最终的预测结果。建立包括单一的支持向量回归机模型、不同分解方法以及相同的分解方法但使用不同的优化算法在内的9种基本模型,来验证所提出的混合模型的优越性。实证研究表明,所提出的混合模型在预测精度上显著优于其他的基本模型。
[Abstract]:In order to improve the reliability and accuracy of the prediction, a hybrid model based on modal decomposition theory and membrane optimization algorithm is proposed for wind speed prediction. Compared with the existing wind speed prediction methods, the prediction accuracy of the model is improved. The model consists of three main steps: to simplify the complexity of the data, The original wind power time series is decomposed into several inherent mode functions by using the complementary set empirical mode decomposition (CEEMD), and the model of the membrane calculation optimization algorithm is established separately for each IMF component to optimize the support vector machine (SVM). The predicted values of all IMF components are superimposed as the final prediction results. Nine basic models, including single support vector regression model, different decomposition methods and the same decomposition methods but using different optimization algorithms, are established to verify the superiority of the proposed hybrid model. Empirical studies show that the proposed hybrid model is superior to other basic models in prediction accuracy.
【作者单位】：广东工业大学自动化学院;
【基金】：广东省科技计划项目(2016A010104016) 广东电网公司科技项目(GDKJQQ20152066)
【分类号】：TM614;TP18

【相似文献】